Imagen de Portada

STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Jinhao, Cong, Yuxuan, Wang, Yingqiao, Xia, Hao, Huang, Shan, Zhang, Yijia, Xu, Ningyi, Dai, Guohao
Formato:	Preprint
Publicado:	2026
Materias:	Robotics Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation
por: Prasad, Aaditya, et al.
Publicado: (2024)

FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency
por: Su, Yifei, et al.
Publicado: (2025)

LeTO: Learning Constrained Visuomotor Policy with Differentiable Trajectory Optimization
por: Xu, Zhengtong, et al.
Publicado: (2024)

Do You Need Proprioceptive States in Visuomotor Policies?
por: Zhao, Juntu, et al.
Publicado: (2025)

One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies
por: Li, Shaolong, et al.
Publicado: (2026)

Constraint-Preserving Data Generation for Visuomotor Policy Learning
por: Lin, Kevin, et al.
Publicado: (2025)

CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-World
por: Fu, Yankai, et al.
Publicado: (2025)

Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
por: Kim, Moo Jin, et al.
Publicado: (2026)

VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memory
por: Lei, Yuheng, et al.
Publicado: (2026)

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
por: Cai, Shaofei, et al.
Publicado: (2025)

MARCA: Mamba Accelerator with ReConfigurable Architecture
por: Li, Jinhao, et al.
Publicado: (2024)

AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving
por: Chai, Jinhao, et al.
Publicado: (2025)

Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learning
por: Gao, George Jiayuan, et al.
Publicado: (2024)

Cross Domain Policy Transfer with Effect Cycle-Consistency
por: Zhu, Ruiqi, et al.
Publicado: (2024)

Deep Learning Warm Starts for Trajectory Optimization on the International Space Station
por: Banerjee, Somrita, et al.
Publicado: (2025)

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
por: Zhong, Yiming, et al.
Publicado: (2025)

Visuomotor Grasping with World Models for Surgical Robots
por: Lin, Hongbin, et al.
Publicado: (2025)

H$^3$DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning
por: Lu, Yiyang, et al.
Publicado: (2025)

IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation
por: Rana, Krishan, et al.
Publicado: (2025)

Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning
por: Liu, Yijun, et al.
Publicado: (2025)

ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation
por: Lu, Guanxing, et al.
Publicado: (2024)

GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks
por: Buoso, Davide, et al.
Publicado: (2026)

WarmPrior: Straightening Flow-Matching Policies with Temporal Priors
por: Kang, Sinjae, et al.
Publicado: (2026)

ZeroWBC: Learning Natural Visuomotor Humanoid Control Directly from Human Egocentric Video
por: Yang, Haoran, et al.
Publicado: (2026)

Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
por: Tian, Ran, et al.
Publicado: (2024)

ImitDiff: Transferring Foundation-Model Priors for Distraction Robust Visuomotor Policy
por: Dong, Yuhang, et al.
Publicado: (2025)

Geometry Guided Self-Consistency for Physical AI
por: Dai, Yinwei, et al.
Publicado: (2026)

Tube-NeRF: Efficient Imitation Learning of Visuomotor Policies from MPC using Tube-Guided Data Augmentation and NeRFs
por: Tagliabue, Andrea, et al.
Publicado: (2023)

Embodied Human Simulation for Quantitative Design and Analysis of Interactive Robotics
por: Zuo, Chenhui, et al.
Publicado: (2026)

ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment
por: Cai, Shaofei, et al.
Publicado: (2025)

The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning
por: Tsagkas, Nikolaos, et al.
Publicado: (2025)

Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion
por: Chen, Kaiqi, et al.
Publicado: (2024)

ViTaS: Visual Tactile Soft Fusion Contrastive Learning for Visuomotor Learning
por: Tian, Yufeng, et al.
Publicado: (2026)

Towards High-Consistency Embodied World Model with Multi-View Trajectory Videos
por: Su, Taiyi, et al.
Publicado: (2025)

PocketDP3: Efficient Pocket-Scale 3D Visuomotor Policy
por: Zhang, Jinhao, et al.
Publicado: (2026)

Towards Consistent and Explainable Motion Prediction using Heterogeneous Graph Attention
por: Demmler, Tobias, et al.
Publicado: (2024)

ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
por: Chen, Yuhui, et al.
Publicado: (2025)

Versatile Navigation under Partial Observability via Value-guided Diffusion Policy
por: Zhang, Gengyu, et al.
Publicado: (2024)

Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation
por: Zhang, Hao, et al.
Publicado: (2024)

RFUAV: A Benchmark Dataset for Unmanned Aerial Vehicle Detection and Identification
por: Shi, Rui, et al.
Publicado: (2025)